[State of RL/Reasoning] IMO/IOI Gold, OpenAI o3/GPT-5, and Cursor Composer — Ashvin Nair, Cursor
December 30, 2025
AI Summary
5 min read🎙️ The Voices & The Context
- The Format: This casual conference-side interview at NeurIPS dives into AI research evolution, blending personal career anecdotes with technical breakdowns of robotics, language models, and RL breakthroughs. Technical yet conversational, it feels like an insider chat unpacking hype versus reality in AI labs.
- The Key Players:
- Guest: Astrain (Cursor AI researcher): Ex-OpenAI engineer with Berkeley PhD in RL-focused robotics; previously interned at OpenAI in 2017; known for hands-on work in code gen, reasoning models like o1/o3, and now pioneering agentic coding tools at Cursor—fascinating for bridging gritty robotics data-grinding to frontier LLM scaling.
Continue reading the full summary in the app — free to try.
Read Full Summary →Free • No credit card required
Never miss an episode of Latent Space: The AI Engineer Podcast
Get every new episode summarized in your inbox — free, ~5 minutes to read.
No spam. Unsubscribe anytime.
What you'll learn
- 1 (00:00) **🎙️ Introduction: Astrid from Cursor**
- 2 (00:25) **Switching from Robotics to Language Models**
- 3 (03:15) **OpenAI Restarting Robotics Team & Market Hype**
- 4 (06:00) **Joining OpenAI & Early Code Gen Work**
- 5 (09:00) **RL Research Pitfalls & Academia Incentives**
- 6 (11:30) **Scaling Era & RL on LMs**
- 7 (16:00) **End of "One Model Fits All"?**
+ Full timestamped outline available in the app
Show Notes
From Berkeley robotics and OpenAI's 2017 Dota-era internship to shipping RL breakthroughs on GPT-4o, o1, and o3, and now leading model development at Cursor, Ashvin Nair has done it all. We caught up with Ashvin at NeurIPS 2025 to dig into the inside story of OpenAI's reasoning team (spoiler: it went from a dozen people to 300+), why IOI Gold felt reachable in 2022 but somehow didn't change the world when o1 actually achieved it, how RL doesn't generalize beyond the training distribution (and why that means you need to bring economically useful tasks into distribution by co-designing products and models), the deeper lessons from the RL research era (2017–2022) and why most of it didn't pan out because the community overfitted to benchmarks, how Cursor is uniquely positioned to do continual learning at scale with policy updates every two hours and product-model co-design that keeps engineers in the loop instead of context-switching into ADHD hell, and his bet that the next paradigm shift is continual learning with infinite memory—where models experience something once (a bug, a mistake, a user pattern) and never forget it, storing millions of deployment tokens in weights without overloading capacity.
We discuss:
Ashvin's path: Berkeley robotics PhD → OpenAI 2017 intern (Dota era) → o1/o3 reasoning team → Cursor ML lead in three months
Why robotics people are the most grounded at NeurIPS (they work with the real world) and simulation people are the most unhinged (Lex Fridman's take)
The IOI Gold paradox: "If you told me we'd achieve IOI Gold in 2022, I'd assume we could all go on vacation—AI solved, no point working anymore. But life is still the same."
The RL research era (2017–2022) and why most of it didn't pan out: overfitting to benchmarks, too many implicit knobs to tune, and the community rewarding complex ideas over simple ones that generalize
Inside the o1 origin story: a dozen people, conviction from Ilya and Jakob Pachocki that RL would work, small-scale prototypes producing "surprisingly accurate reasoning traces" on math, and first-principles belief that scaled
The reasoning team grew from ~12 to 300+ people as o1 became a product and safety, tooling, and deployment scaled up
Why Cursor is uniquely positioned for continual learning: policy updates every two hours (